A simple linear averaging of the outputs of several networks as e.g. in bagging [3], seems to follow naturally from a bias/variance decomposition of the sum-squared error. The sum-squared error of the average model is a quadratic function of the weighting factors assigned to the networks in the ensemble [7], suggesting a quadratic programming algorithm for finding the "optimal" weighting factors. If we interpret the output of a network as a probability statement, the sum-squared error corresponds to minus the loglikelihood or the Kullback-Leibler divergence, and linear averaging of the outputs tologarithmic averaging of the probability statements: the logarithmic opinion pool. The crux of this paper is that this whole story about model averaging, bias/variancedecompositions, and quadratic programming to find the optimal weighting factors, is not specific for the sumsquared error,but applies to the combination of probability statements of any kind in a logarithmic opinion pool, as long as the Kullback-Leibler divergence plays the role of the error measure. As examples we treat model averaging for classification models under a cross-entropy error measure and models for estimating variances.

Recent theoretical results for pattern classification with thresholded real-valuedfunctions (such as support vector machines, sigmoid networks,and boosting) give bounds on misclassification probability that do not depend on the size of the classifier, and hence can be considerably smaller than the bounds that follow from the VC theory. In this paper, we show that these techniques can be more widely applied, by representing other boolean functions as two-layer neural networks (thresholded convex combinations of boolean functions).

Our model consists of a classical energy mechanism whose output is divided by nonclassical gain control and texture contrast mechanisms. We apply this model to review movies, a stimulus sequence that replicates the stimulation a cell receives during free viewing of natural images. Data were collected from three cells using five different review movies, and the model was fit separately to the data from each movie. For the energy mechanism alone we find modest but significant correlations (rE 0.41, 0.43, 0.59, 0.35) between model and data. These correlations are improved somewhat when we allow for suppressive surround effects (rE G 0.42, 0.56, 0.60, 0.37). In one case the inclusion of a delayed suppressive surround dramatically improves the fit to the data by modifying the time course of the model's response.

We discuss a solution to the problem of separating waveforms produced bymultiple cells in an extracellular neural recording. We take an explicitly probabilistic approach, using latent-variable models ofvarying sophistication to describe the distribution of waveforms producedby a single cell. The models range from a single Gaussian distribution of waveforms for each cell to a mixture of hidden Markov models. We stress the overall statistical structure of the approach, allowing the details of the generative model chosen to depend on the specific neural preparation.

In macaque inferotemporal cortex (IT), neurons have been found to respond selectivelyto complex shapes while showing broad tuning ("invariance") withrespect to stimulus transformations such as translation and scale changes and a limited tuning to rotation in depth.

To understand human object recognition, it is essential to understand how objects are represented in human visual memory. A central component in object recognition is the matching of the stored object representation with that derived from the image input.But the nature of the object representation has to be inferred from recognition performance, by taking into account the contribution from the image information. When evaluating human performance, how can one separate the con- 830 ZLiu and D. Kersten tributions to performance of the image information from the representation? Ideal observer analysis provides a precise computational tool to answer this question. An ideal observer's recognition performance is restricted only by the available image information and is otherwise optimal, in the sense of statistical decision theory, irrespective of how the model is implemented.

In most neural network models, synapses are treated as static weights that change only on the slow time scales of learning. In fact, however, synapses are highly dynamic, and show use-dependent plasticity over a wide range of time scales. Moreover, synaptic transmission is an inherently stochastic process: a spike arriving at a presynaptic terminal triggers release of a vesicle of neurotransmitter from a release site with a probability that can be much less than one. Changes in release probability represent one of the main mechanisms by which synaptic efficacy is modulated in neural circuits. We propose and investigate a simple model for dynamic stochastic synapses that can easily be integrated into common models for neural computation. We show through computer simulations and rigorous theoretical analysis that this model for a dynamic stochastic synapse increases computational power in a nontrivial way. Our results may have implications for the processing oftime-varying signals by both biological and artificial neural networks. A synapse 8 carries out computations on spike trains, more precisely on trains of spikes from the presynaptic neuron. Each spike from the presynaptic neuron mayor may not trigger the release of a neurotransmitter-filled vesicle at the synapse.

We propose a model for early visual processing in primates. The model consists of a population of linear spatial filters which interact throughnon-linear excitatory and inhibitory pooling. Statistical estimation theory is then used to derive human psychophysical thresholds from the responses of the entire population of units. The model is able to reproduce human thresholds for contrast and orientation discriminationtasks, and to predict contrast thresholds in the presence of masks of varying orientation and spatial frequency.

Brody t SamRoweis t Abstract Most computational engineering based loosely on biology uses continuous variablesto represent neural activity. Yet most neurons communicate with action potentials. The engineering view is equivalent to using a rate-code for representing information and for computing. An increasing numberof examples are being discovered in which biology may not be using rate codes. Information can be represented using the timing of action potentials, and efficiently computed with in this representation. The "analog match" problem of odour identification is a simple problem which can be efficiently solved using action potential timing and an underlying rhythm.By using adapting units to effect a fundamental change of representation of a problem, we map the recognition of words (having uniformtime-warp) in connected speech into the same analog match problem.

One of the current challenges to understanding neural information processing in biological systems is to decipher the "code" carried by large populations of neurons acting in parallel. We present an algorithm for automated discovery of stochastic firing patterns in large ensembles of neurons. The algorithm, from the "Helmholtz Machine" family, attempts to predict the observed spike patterns in the data. The model consists of an observable layer which is directly activated by the input spike patterns, and hidden units that are activated throughascending connections from the input layer. The hidden unit activity can be propagated down to the observable layer to create a prediction of the data pattern that produced it.